Spatial hyperspectral image classification by prior segmentation
In this paper, we propose a technique to incorporate spatial features in the classification of hyperspectral data by means of a prior segmentation of the dataset. The key idea of the technique is that each pixel is not classified individually, but that the regions obtained from the prior segmentatio...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | III-712 |
|---|---|
| container_issue | |
| container_start_page | III-709 |
| container_title | |
| container_volume | 3 |
| creator | Driesen, J. Thoonen, G. Scheunders, P. |
| description | In this paper, we propose a technique to incorporate spatial features in the classification of hyperspectral data by means of a prior segmentation of the dataset. The key idea of the technique is that each pixel is not classified individually, but that the regions obtained from the prior segmentation are classified as a whole. The proposed technique is validated on a hyperspectral dataset of a heathland area in Belgium. Experimental results show that we can achieve larger and spatially smoothed regions, while the overall classification success rate is comparable to the pure spectral classification results. |
| doi_str_mv | 10.1109/IGARSS.2009.5417861 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5417861</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5417861</ieee_id><sourcerecordid>5417861</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-95d26ef733ca3800d52d5d9bdcb17efab26bdcfe28c653cca33cd55ae2d6f8a23</originalsourceid><addsrcrecordid>eNpFUMtqwzAQVB-BJmm-IBf_gF29Zd0aQpMGAoW6PQdZWqUqdmIsX_z3Fa2he5ndmWEYFqE1wQUhWD8d9pv3qiooxroQnKhSkhu0IJxyzpgW-hbNKREsVxizu3-B4_tJkFrLGVqkgFITnKgHtIrxG6fhAkuu5ui56swQTJN9jR30sQM79OkKrTlDZhsTY_DBJsv1ktVj1vXh2mcRzi1chl_2Ec28aSKsJlyiz93Lx_Y1P77tD9vNMQ9EiSHXwlEJXjFmDSsxdoI64XTtbE0UeFNTmXYPtLRSMJtMzDohDFAnfWkoW6L1X24AgFPq0Zp-PE1vYT9YjFJt</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Spatial hyperspectral image classification by prior segmentation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Driesen, J. ; Thoonen, G. ; Scheunders, P.</creator><creatorcontrib>Driesen, J. ; Thoonen, G. ; Scheunders, P.</creatorcontrib><description>In this paper, we propose a technique to incorporate spatial features in the classification of hyperspectral data by means of a prior segmentation of the dataset. The key idea of the technique is that each pixel is not classified individually, but that the regions obtained from the prior segmentation are classified as a whole. The proposed technique is validated on a hyperspectral dataset of a heathland area in Belgium. Experimental results show that we can achieve larger and spatially smoothed regions, while the overall classification success rate is comparable to the pure spectral classification results.</description><identifier>ISSN: 2153-6996</identifier><identifier>ISBN: 1424433940</identifier><identifier>ISBN: 9781424433940</identifier><identifier>EISSN: 2153-7003</identifier><identifier>EISBN: 1424433959</identifier><identifier>EISBN: 9781424433957</identifier><identifier>DOI: 10.1109/IGARSS.2009.5417861</identifier><identifier>LCCN: 2008910215</identifier><language>eng</language><publisher>IEEE</publisher><subject>Classification algorithms ; Clustering algorithms ; Covariance matrix ; Hyperspectral imaging ; Hyperspectral sensors ; Image classification ; Image segmentation ; Maximum likelihood estimation ; Multispectral imaging ; Pixel ; Remote sensing</subject><ispartof>2009 IEEE International Geoscience and Remote Sensing Symposium, 2009, Vol.3, p.III-709-III-712</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5417861$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5417861$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Driesen, J.</creatorcontrib><creatorcontrib>Thoonen, G.</creatorcontrib><creatorcontrib>Scheunders, P.</creatorcontrib><title>Spatial hyperspectral image classification by prior segmentation</title><title>2009 IEEE International Geoscience and Remote Sensing Symposium</title><addtitle>IGARSS</addtitle><description>In this paper, we propose a technique to incorporate spatial features in the classification of hyperspectral data by means of a prior segmentation of the dataset. The key idea of the technique is that each pixel is not classified individually, but that the regions obtained from the prior segmentation are classified as a whole. The proposed technique is validated on a hyperspectral dataset of a heathland area in Belgium. Experimental results show that we can achieve larger and spatially smoothed regions, while the overall classification success rate is comparable to the pure spectral classification results.</description><subject>Classification algorithms</subject><subject>Clustering algorithms</subject><subject>Covariance matrix</subject><subject>Hyperspectral imaging</subject><subject>Hyperspectral sensors</subject><subject>Image classification</subject><subject>Image segmentation</subject><subject>Maximum likelihood estimation</subject><subject>Multispectral imaging</subject><subject>Pixel</subject><subject>Remote sensing</subject><issn>2153-6996</issn><issn>2153-7003</issn><isbn>1424433940</isbn><isbn>9781424433940</isbn><isbn>1424433959</isbn><isbn>9781424433957</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFUMtqwzAQVB-BJmm-IBf_gF29Zd0aQpMGAoW6PQdZWqUqdmIsX_z3Fa2he5ndmWEYFqE1wQUhWD8d9pv3qiooxroQnKhSkhu0IJxyzpgW-hbNKREsVxizu3-B4_tJkFrLGVqkgFITnKgHtIrxG6fhAkuu5ui56swQTJN9jR30sQM79OkKrTlDZhsTY_DBJsv1ktVj1vXh2mcRzi1chl_2Ec28aSKsJlyiz93Lx_Y1P77tD9vNMQ9EiSHXwlEJXjFmDSsxdoI64XTtbE0UeFNTmXYPtLRSMJtMzDohDFAnfWkoW6L1X24AgFPq0Zp-PE1vYT9YjFJt</recordid><startdate>200907</startdate><enddate>200907</enddate><creator>Driesen, J.</creator><creator>Thoonen, G.</creator><creator>Scheunders, P.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200907</creationdate><title>Spatial hyperspectral image classification by prior segmentation</title><author>Driesen, J. ; Thoonen, G. ; Scheunders, P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-95d26ef733ca3800d52d5d9bdcb17efab26bdcfe28c653cca33cd55ae2d6f8a23</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Classification algorithms</topic><topic>Clustering algorithms</topic><topic>Covariance matrix</topic><topic>Hyperspectral imaging</topic><topic>Hyperspectral sensors</topic><topic>Image classification</topic><topic>Image segmentation</topic><topic>Maximum likelihood estimation</topic><topic>Multispectral imaging</topic><topic>Pixel</topic><topic>Remote sensing</topic><toplevel>online_resources</toplevel><creatorcontrib>Driesen, J.</creatorcontrib><creatorcontrib>Thoonen, G.</creatorcontrib><creatorcontrib>Scheunders, P.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Driesen, J.</au><au>Thoonen, G.</au><au>Scheunders, P.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Spatial hyperspectral image classification by prior segmentation</atitle><btitle>2009 IEEE International Geoscience and Remote Sensing Symposium</btitle><stitle>IGARSS</stitle><date>2009-07</date><risdate>2009</risdate><volume>3</volume><spage>III-709</spage><epage>III-712</epage><pages>III-709-III-712</pages><issn>2153-6996</issn><eissn>2153-7003</eissn><isbn>1424433940</isbn><isbn>9781424433940</isbn><eisbn>1424433959</eisbn><eisbn>9781424433957</eisbn><abstract>In this paper, we propose a technique to incorporate spatial features in the classification of hyperspectral data by means of a prior segmentation of the dataset. The key idea of the technique is that each pixel is not classified individually, but that the regions obtained from the prior segmentation are classified as a whole. The proposed technique is validated on a hyperspectral dataset of a heathland area in Belgium. Experimental results show that we can achieve larger and spatially smoothed regions, while the overall classification success rate is comparable to the pure spectral classification results.</abstract><pub>IEEE</pub><doi>10.1109/IGARSS.2009.5417861</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2153-6996 |
| ispartof | 2009 IEEE International Geoscience and Remote Sensing Symposium, 2009, Vol.3, p.III-709-III-712 |
| issn | 2153-6996 2153-7003 |
| language | eng |
| recordid | cdi_ieee_primary_5417861 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Classification algorithms Clustering algorithms Covariance matrix Hyperspectral imaging Hyperspectral sensors Image classification Image segmentation Maximum likelihood estimation Multispectral imaging Pixel Remote sensing |
| title | Spatial hyperspectral image classification by prior segmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-19T03%3A31%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Spatial%20hyperspectral%20image%20classification%20by%20prior%20segmentation&rft.btitle=2009%20IEEE%20International%20Geoscience%20and%20Remote%20Sensing%20Symposium&rft.au=Driesen,%20J.&rft.date=2009-07&rft.volume=3&rft.spage=III-709&rft.epage=III-712&rft.pages=III-709-III-712&rft.issn=2153-6996&rft.eissn=2153-7003&rft.isbn=1424433940&rft.isbn_list=9781424433940&rft_id=info:doi/10.1109/IGARSS.2009.5417861&rft_dat=%3Cieee_6IE%3E5417861%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424433959&rft.eisbn_list=9781424433957&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5417861&rfr_iscdi=true |